Name
Title | ||
|---|---|---|
Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations. |
Abstract | ||
|---|---|---|
Universal perceptron (UP), a generalization of Rosenblatt's perceptron, is considered in this paper, which is capable of implementing all Boolean functions (BFs). In the classification of BFs, there are: 1) linearly separable Boolean function (LSBF) class, 2) parity Boolean function (PBF) class, and 3) non-LSBF and non-PBF class. To implement these functions, UP takes different kinds of simple topological structures in which each contains at most one hidden layer along with the smallest possible number of hidden neurons. Inspired by the concept of DNA sequences in biological systems, a novel learning algorithm named DNA-like learning is developed, which is able to quickly train a network with any prescribed BF. The focus is on performing LSBF and PBF by a single-layer perceptron (SLP) with the new algorithm. Two criteria for LSBF and PBF are proposed, respectively, and a new measure for a BF, named nonlinearly separable degree (NLSD), is introduced. In the sense of this measure, the PBF is the most complex one. The new algorithm has many advantages including, in particular, fast running speed, good robustness, and no need of considering the convergence property. For example, the number of iterations and computations in implementing the basic 2-bit logic operations such as AND, OR, and XOR by using the new algorithm is far smaller than the ones needed by using other existing algorithms such as error-correction (EC) and backpropagation (BP) algorithms. Moreover, the synaptic weights and threshold values derived from UP can be directly used in designing of the template of cellular neural networks (CNNs), which has been considered as a new spatial-temporal sensory computing paradigm. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/TNN.2009.2028886 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
universal perceptron,existing algorithm,new spatial-temporal sensory computing,new measure,dna-like learning,pbf implementation,non-pbf class,parity boolean function,binary neural network,new algorithm,single-layer perceptron,boolean function,biological system,sequences,slp,topology,dna,learning artificial intelligence,cellular neural networks,neural networks,synaptic weight,logic,mathematics,multilayer perceptron,biological systems,cellular neural network,backpropagation,dna sequence,linear discriminant analysis,helium,neural network,robustness,up,convergence,threshold value,error correction,backpropagation algorithm,boolean functions | Boolean function,Linear separability,Computer science,Theoretical computer science,Multilayer perceptron,Artificial intelligence,Artificial neural network,Algorithm,Boolean algebra,Backpropagation,Perceptron,Cellular neural network,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 10 | 1941-0093 |
Citations | PageRank | References |
17 | 0.93 | 26 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fang-yue Chen | 1 | 80 | 18.67 |
| Guanrong Chen | 2 | 12378 | 1130.81 |
| Guolong He | 3 | 30 | 3.67 |
| Xiubin Xu | 4 | 29 | 3.23 |
| Qinbin He | 5 | 23 | 3.46 |